Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ጋር
    0.42
     Боль
    0.39
     HTMLSc
    0.36
     മാ
    0.36
     medically
    0.35
    Freeze
    0.35
    Pixmap
    0.34
     numerically
    0.34
     !='')
    0.34
     Veľ
    0.34
    POSITIVE LOGITS
    语言
    0.48
     language
    0.46
    語言
    0.45
    anguage
    0.45
     Language
    0.44
    言語
    0.43
     Grammar
    0.42
    language
    0.41
    Language
    0.41
     Sprache
    0.41
    Act Density 0.004%

    No Known Activations